the real signal here isn't a skill catalog. it's that "skill" is now a software supply chain. and supply chains get attacked. if you run agents on a real codebase, start treating every skill you…

NVIDIA built exactly what I needed to secure agent skills Adding it as a GitHub Action to Every community-submitted skill gets scanned before it goes live No prompt injection, no data exfiltration,…

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.

This is good, worth adding as CI step for all skills repo.

AI governance is on it's way